LoRA of Meika Woollard (Older) (For SD1.5)

Description

You can get this LoRA for $0 here. Also you can download and test it for FREE via CivitAI ; or via TensorArt.

This LoRA trained using kohya_ss on 60 images 768×768 for 2 epochs 1560 steps each with manually enhanced blip2 and/or llava captions and without regularization images.
Source model: ‘v1-5-pruned-emaonly’ checkpoint (SD1.5), so this LoRA should works well with most of Stable Diffusion v1.5 forks and mixes.
Learning rate: 2e-05 or 0.00001.
Precision: fp16.
LR Scheduler: constant_with_warmup.
LR warmup: 30%.

Preview images were rendered on checkpoints: pirsusEpicRealism_v31Pruned (hash: 582daed225)
If you are going to remake preview images you should have:
checkpoint: pirsusEpicRealism_v31Pruned
lora: AIDA_LoRA_MeW2023
embeddings: kkw-ph1

Download link to AIDA_LoRA_MeW2023 LoRA will be available for you after purchase. For your comfort I packed AIDA_LoRA_MeW2023.safetensors into .zip archive with AIDA_LoRA_MeW2023.png and AIDA_LoRA_MeW2023.txt , preview and description are compatible with AUTOMATIC1111 extra networks menu.
Also you will get .zip archive with all preview images and generation data for them.

Please pay at least 1$ If you want to achieve rights for selling images generated with AIDA_LoRA_MeW2023 LoRA. Also this way you can say me special thanks for this LoRA.

Please contact me if you need some extended rights for sharing or selling AIDA_LoRA_MeW2023, merging AIDA_LoRA_MeW2023 with other models, using AIDA_LoRA_MeW2023 in generation services and so on.